From 03a4107753df4a1eed737e2940a1b690c0deb70e Mon Sep 17 00:00:00 2001 From: Kevin Jain Date: Thu, 4 Sep 2025 09:52:07 -0500 Subject: [PATCH] Add Embeddinggemma-300m model to Workers AI docs This PR also adds changes in schemas for partner models --- .../embeddinggemma-300m.json | 58 +++++++++++++++++++ .../workers-ai-models/lucid-origin.json | 15 +++-- src/content/workers-ai-models/nova-3.json | 22 ++++++- .../workers-ai-models/smart-turn-v2.json | 4 ++ 4 files changed, 93 insertions(+), 6 deletions(-) create mode 100644 src/content/workers-ai-models/embeddinggemma-300m.json diff --git a/src/content/workers-ai-models/embeddinggemma-300m.json b/src/content/workers-ai-models/embeddinggemma-300m.json new file mode 100644 index 00000000000000..608e7315b7192c --- /dev/null +++ b/src/content/workers-ai-models/embeddinggemma-300m.json @@ -0,0 +1,58 @@ +{ + "id": "d2f07a41-c152-4061-8083-ec655cbf91a1", + "source": 1, + "name": "@cf/google/embeddinggemma-300m", + "description": "EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.", + "task": { + "id": "0137cdcf-162a-4108-94f2-1ca59e8c65ee", + "name": "Text Embeddings", + "description": "Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)." + }, + "created_at": "2025-09-03 20:48:38.784", + "tags": [], + "properties": [], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "oneOf": [{ + "type": "string" + }, { + "type": "array", + "items": { + "type": "string" + } + }], + "description": "Input text to embed. Can be a single string or a list of strings." + } + }, + "required": ["text"] + }, + "output": { + "type": "object", + "properties": { + "data": { + "type": "array", + "items": { + "type": "array", + "items": { + "type": "number" + } + }, + "description": "Embedding vectors, where each vector is a list of floats." + }, + "shape": { + "type": "array", + "items": { + "type": "integer" + }, + "minItems": 2, + "maxItems": 2, + "description": "Shape of the embedding data as [number_of_embeddings, embedding_dimension]." + } + }, + "required": ["data", "shape"] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/lucid-origin.json b/src/content/workers-ai-models/lucid-origin.json index a2b1780a5f3b6e..3a2a138089c50a 100644 --- a/src/content/workers-ai-models/lucid-origin.json +++ b/src/content/workers-ai-models/lucid-origin.json @@ -11,10 +11,6 @@ "created_at": "2025-08-25 19:21:28.770", "tags": [], "properties": [ - { - "property_id": "partner", - "value": "true" - }, { "property_id": "price", "value": [ @@ -29,6 +25,10 @@ "currency": "USD" } ] + }, + { + "property_id": "partner", + "value": "true" } ], "schema": { @@ -68,7 +68,12 @@ }, "num_steps": { "type": "integer", - "default": 4, + "minimum": 1, + "maximum": 40, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "steps": { + "type": "integer", "minimum": 1, "maximum": 40, "description": "The number of diffusion steps; higher values can improve quality but take longer" diff --git a/src/content/workers-ai-models/nova-3.json b/src/content/workers-ai-models/nova-3.json index 653516920e6acb..309f60ca679c0d 100644 --- a/src/content/workers-ai-models/nova-3.json +++ b/src/content/workers-ai-models/nova-3.json @@ -111,7 +111,7 @@ "type": "string", "description": "Arbitrary key-value pairs that are attached to the API response for usage in downstream processing" }, - "filter_words": { + "filler_words": { "type": "boolean", "description": "Filler Words can help transcribe interruptions in your audio, like 'uh' and 'um'" }, @@ -195,6 +195,26 @@ "utt_split": { "type": "number", "description": "Seconds to wait before detecting a pause between words in submitted audio." + }, + "channels": { + "type": "number", + "description": "The number of channels in the submitted audio" + }, + "interim_results": { + "type": "boolean", + "description": "Specifies whether the streaming endpoint should provide ongoing transcription updates as more audio is received. When set to true, the endpoint sends continuous updates, meaning transcription results may evolve over time. Note: Supported only for webosockets." + }, + "endpointing": { + "type": "string", + "description": "Indicates how long model will wait to detect whether a speaker has finished speaking or pauses for a significant period of time. When set to a value, the streaming endpoint immediately finalizes the transcription for the processed time range and returns the transcript with a speech_final parameter set to true. Can also be set to false to disable endpointing" + }, + "vad_events": { + "type": "boolean", + "description": "Indicates that speech has started. You'll begin receiving Speech Started messages upon speech starting. Note: Supported only for webosockets." + }, + "utterance_end_ms": { + "type": "boolean", + "description": "Indicates how long model will wait to send an UtteranceEnd message after a word has been transcribed. Use with interim_results. Note: Supported only for webosockets." } }, "required": [ diff --git a/src/content/workers-ai-models/smart-turn-v2.json b/src/content/workers-ai-models/smart-turn-v2.json index fe90b53f827fb9..279d415a1bcc7c 100644 --- a/src/content/workers-ai-models/smart-turn-v2.json +++ b/src/content/workers-ai-models/smart-turn-v2.json @@ -24,6 +24,10 @@ "currency": "USD" } ] + }, + { + "property_id": "realtime", + "value": "true" } ], "schema": {